docstrings: document_loaders consitency 2 (#9148)

This is Part 2. See #9139 (Part 1).

Author: leo-gan

libs/langchain/langchain/document_loaders/hugging_face_dataset.py

@@ -1,12 +1,11 @@
-"""Loads HuggingFace datasets."""
 from typing import Iterator, List, Mapping, Optional, Sequence, Union
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.base import BaseLoader
 
 
 class HuggingFaceDatasetLoader(BaseLoader):
-    """Load Documents from the Hugging Face Hub."""
+    """Load from `Hugging Face Hub` datasets."""
 
     def __init__(
         self,

libs/langchain/langchain/document_loaders/ifixit.py

@@ -1,4 +1,3 @@
-"""Loads iFixit data."""
 from typing import List, Optional
 
 import requests
@@ -11,7 +10,7 @@
 
 
 class IFixitLoader(BaseLoader):
-    """Load iFixit repair guides, device wikis and answers.
+    """Load `iFixit` repair guides, device wikis and answers.
 
     iFixit is the largest, open repair community on the web. The site contains nearly
     100k repair manuals, 200k Questions & Answers on 42k devices, and all the data is

libs/langchain/langchain/document_loaders/image.py

@@ -1,11 +1,10 @@
-"""Loads image files."""
 from typing import List
 
 from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class UnstructuredImageLoader(UnstructuredFileLoader):
-    """Loader that uses Unstructured to load PNG and JPG files.
+    """Load `PNG` and `JPG` files using `Unstructured`.
 
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single

libs/langchain/langchain/document_loaders/image_captions.py

@@ -1,9 +1,3 @@
-"""Loads image captions.
-
-By default, the loader utilizes the pre-trained BLIP image captioning model.
-https://huggingface.co/Salesforce/blip-image-captioning-base
-
-"""
 from typing import Any, List, Tuple, Union
 
 import requests
@@ -13,7 +7,12 @@
 
 
 class ImageCaptionLoader(BaseLoader):
-    """Loads the captions of an image"""
+    """Load image captions.
+
+    By default, the loader utilizes the pre-trained
+    Salesforce BLIP image captioning model.
+    https://huggingface.co/Salesforce/blip-image-captioning-base
+    """
 
     def __init__(
         self,

libs/langchain/langchain/document_loaders/imsdb.py

@@ -1,12 +1,11 @@
-"""Loads IMSDb."""
 from typing import List
 
 from langchain.docstore.document import Document
 from langchain.document_loaders.web_base import WebBaseLoader
 
 
 class IMSDbLoader(WebBaseLoader):
-    """Loads IMSDb webpages."""
+    """Load `IMSDb` webpages."""
 
     def load(self) -> List[Document]:
         """Load webpage."""

libs/langchain/langchain/document_loaders/iugu.py

@@ -1,4 +1,3 @@
-"""Loader that fetches data from IUGU"""
 import json
 import urllib.request
 from typing import List, Optional
@@ -17,7 +16,7 @@
 
 
 class IuguLoader(BaseLoader):
-    """Loader that fetches data from IUGU."""
+    """Load from `IUGU`."""
 
     def __init__(self, resource: str, api_token: Optional[str] = None) -> None:
         """Initialize the IUGU resource.

libs/langchain/langchain/document_loaders/joplin.py

@@ -11,8 +11,7 @@
 
 
 class JoplinLoader(BaseLoader):
-    """
-    Loader that fetches notes from Joplin.
+    """Load notes from `Joplin`.
 
     In order to use this loader, you need to have Joplin running with the
     Web Clipper enabled (look for "Web Clipper" in the app settings).

libs/langchain/langchain/document_loaders/json_loader.py

@@ -1,4 +1,3 @@
-"""Loads data from JSON."""
 import json
 from pathlib import Path
 from typing import Any, Callable, Dict, List, Optional, Union
@@ -8,7 +7,7 @@
 
 
 class JSONLoader(BaseLoader):
-    """Loads a JSON file using a jq schema.
+    """Load a `JSON` file using a `jq` schema.
 
     Example:
         [{"text": ...}, {"text": ...}, {"text": ...}] -> schema = .[].text

libs/langchain/langchain/document_loaders/larksuite.py

@@ -1,4 +1,3 @@
-"""Loads LarkSuite (FeiShu) document json dump."""
 import json
 import urllib.request
 from typing import Any, Iterator, List
@@ -8,7 +7,7 @@
 
 
 class LarkSuiteDocLoader(BaseLoader):
-    """Loads LarkSuite (FeiShu) document."""
+    """Load from `LarkSuite` (`FeiShu`)."""
 
     def __init__(self, domain: str, access_token: str, document_id: str):
         """Initialize with domain, access_token (tenant / user), and document_id.

libs/langchain/langchain/document_loaders/markdown.py

@@ -1,11 +1,10 @@
-"""Loads Markdown files."""
 from typing import List
 
 from langchain.document_loaders.unstructured import UnstructuredFileLoader
 
 
 class UnstructuredMarkdownLoader(UnstructuredFileLoader):
-    """Loader that uses Unstructured to load markdown files.
+    """Load `Markdown` files using `Unstructured`.
 
     You can run the loader in one of two modes: "single" and "elements".
     If you use "single" mode, the document will be returned as a single